This repository contains code, resources, and documentation for the workshop "Building a Multi-Agent Workforce with Azure AI Foundry".
Table of Contents:
- Azure AI Multi-Agent Workforce
Here are the key areas you might be looking for:
azure-ai-multi-agent-workforce/
βββ config/ # Configuration files for managing the project
βββ multi-agent/ # Multi-agent examples
βββ single-agent/ # Single-agent examples
βββ README.md # Overview and documentation of the repository
- A working Azure subscription
- Access to Azure AI Foundry
- Basic Python knowledge
- Checkout π¬ Video Tutorials & βοΈ Tools & Technologies
- Create Azure for Students Account with a Voucher β Get $100 Free Credit
- Create Azure Free Account β Get $200 Free Credit
- Git β Version control system for tracking code changes
- GitHub β For accessing and managing the project repository
- Visual Studio Code (VS Code) β Recommended code editor for development
- Python - Programming language used for agent development
- uv - A modern, high-performance Python package manager and installer
- Azure CLI β Command-line interface for managing Azure resources
- Azure Account β Required to access and deploy AI services on Microsoft Azure
- Dependencies:
- Python <= 3.13.5
- Python Packages:
- azure-ai-agents >= 1.1.0b4
- azure-ai-projects >= 1.0.0b12
- azure-identity >= 1.24.0b1
- python-dotenv >= 1.1.1
If you already have an Azure account that works with Azure AI Foundry projects, you're good to go!
Otherwise, you'll need to set one up. Watch this video for a step-by-step walkthrough: Create Azure Free Account β Get $200 Free Credit
Follow these steps to set up your Azure AI Foundry project:
- Sign in to the Azure Portal.
- Create a new Resource Group to organize your resources.
- Go to Azure AI Foundry and sign in.
- Create a new project, making sure to select the Resource Group you created earlier.
- Deploy at least one AI model within your project to enable functionality.
Install and configure the required βοΈ Tools & Technologies before running the project locally.
These typically include:
- Python (recommended version: 3.10+)
pip
/uv
/virtualenv
orconda
- Git
- Azure CLI
- Other dependencies listed in
requirements.txt
Make sure to install all dependencies using:
pip install -r requirements.txt
Important
Verify Azure Authentication:
Ensure you are logged in with Azure CLI or your environment supports DefaultAzureCredential: az login
Click Fork on GitHub to create your own copy of this repository under your GitHub account.
Open your terminal and run the following commands:
git clone https://github.com/dileepadev/cinewave-demo.git
cd cinewave-demo
Each subdirectory (such as multi-agent/
and single-agent/
) contains its own .env.example
file. These files define the environment variables required to run the examples in that specific folder.
To get started:
-
Navigate to the subdirectory you're working with (e.g.,
multi-agent/
). -
Copy the example environment file and rename it to
.env
:cp .env.example .env # On Windows: use copy .env.example .env
-
Open the
.env
file in your text editor and update the values with your Azure credentials and other necessary configuration.
Repeat this process for each subdirectory you plan to run.
Follow the instructions in the corresponding subdirectoryβs README.md
or usage guide to run the application.
- Abbreviation recommendations for Azure resources
- Azure documentation
- Azure AI Foundry documentation
- Azure Identity client library for Python - version 1.25.0
- Azure AI Projects client library for Python - version 1.1.0b4
- Azure AI Agents client library for Python - version 1.2.0b4
- What is Azure AI Foundry Agent Service?
- Quickstart: Get started with Azure AI Foundry (Foundry projects)
- Quickstart: Create a new agent
- Build collaborative, multi-agent systems with Connected Agents
- What is Azure AI Foundry?
- Create Azure for Students Account with a Voucher β Get $100 Free Credit
- Create Azure Free Account β Get $200 Free Credit
- Get started with Azure CLI
If you like this project and want to see future updates, please consider giving it a star on GitHub!
This project is licensed under the MIT License.
If you have any questions or suggestions regarding this project, feel free to open an issue or submit a pull request in this repository.
You can also reach me via email at: [email protected]